© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15527
    Prev
    Next
    INDEX
    Explanations

    coined by, coined for, photographic material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -2.86
    ी
    -2.81
     ''
    -2.61
    ي
    -2.61
    溫泉
    -2.52
    的说道
    -2.30
    \
    -2.25
    ς
    -2.23
    い
    -2.23
    好在
    -2.19
    POSITIVE LOGITS
    }$
    2.55
    al
    2.25
    蹰
    2.23
    quelles
    2.23
    zaSy
    2.22
    ών
    2.20
    関わ
    2.17
    </strong>
    2.16
    当局
    2.09
    
    2.09
    Activations Density 0.003%

    No Known Activations